Image Filters

classic Classic list List threaded Threaded
5 messages Options
Reply | Threaded
Open this post in threaded view
|

Image Filters

Strugari, Matthew SCA
Image Filters

Hi,

Is there any image filter or method that can be used to change a detailed US or MR image into a solid coloured binary image? I would like to remove the detail from my volumes so that I am registering with a single coloured/grayscale volume.

Thanks.
Matthew


_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject
http://www.slicer.org/slicerWiki/index.php/Documentation/4.3/FAQ


The information in this e-mail is intended only for the person to whom it is
addressed. If you believe this e-mail was sent to you in error and the e-mail
contains patient information, please contact the Partners Compliance HelpLine at
http://www.partners.org/complianceline . If the e-mail was sent to you in error
but does not contain patient information, please contact the sender and properly
dispose of the e-mail.
Reply | Threaded
Open this post in threaded view
|

Re: Image Filters

Alireza Mehrtash
Hi Matthew,

You can use BinaryThresholdImageFilter from "Simple Filters" module. 

Alireza



On Wed, Jun 18, 2014 at 4:38 PM, Strugari, Matthew SCA <[hidden email]> wrote:

Hi,

Is there any image filter or method that can be used to change a detailed US or MR image into a solid coloured binary image? I would like to remove the detail from my volumes so that I am registering with a single coloured/grayscale volume.

Thanks.
Matthew


_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject
http://www.slicer.org/slicerWiki/index.php/Documentation/4.3/FAQ


The information in this e-mail is intended only for the person to whom it is
addressed. If you believe this e-mail was sent to you in error and the e-mail
contains patient information, please contact the Partners Compliance HelpLine at
http://www.partners.org/complianceline . If the e-mail was sent to you in error
but does not contain patient information, please contact the sender and properly
dispose of the e-mail.



_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject
http://www.slicer.org/slicerWiki/index.php/Documentation/4.3/FAQ


The information in this e-mail is intended only for the person to whom it is
addressed. If you believe this e-mail was sent to you in error and the e-mail
contains patient information, please contact the Partners Compliance HelpLine at
http://www.partners.org/complianceline . If the e-mail was sent to you in error
but does not contain patient information, please contact the sender and properly
dispose of the e-mail.
Reply | Threaded
Open this post in threaded view
|

Re: Image Filters

Dominik Meier
In reply to this post by Strugari, Matthew SCA
Hi Matthew

Sounds like an interesting application. Did you find registration to work better with a binary image than the original one?  I'm wondering if there is not something that can be done at the point of registration that would avoid this step. In general the grayscale information helps make registrations more robust, although there are cases with distracting content that can make things worse. Could you give us a brief description of the data you're registering? Maybe there's alternatives.

Best,
Dominik




On Jun 18, 2014, at 5:34 PM, Alireza Mehrtash <[hidden email]> wrote:

Hi Matthew,

You can use BinaryThresholdImageFilter from "Simple Filters" module. 

Alireza


On Jun 18, 2014, at 4:38 PM, Strugari, Matthew SCA <[hidden email]> wrote:

Image Filters

Hi,

Is there any image filter or method that can be used to change a detailed US or MR image into a solid coloured binary image? I would like to remove the detail from my volumes so that I am registering with a single coloured/grayscale volume.

Thanks.
Matthew

_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject
http://www.slicer.org/slicerWiki/index.php/Documentation/4.3/FAQ


_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject
http://www.slicer.org/slicerWiki/index.php/Documentation/4.3/FAQ


The information in this e-mail is intended only for the person to whom it is
addressed. If you believe this e-mail was sent to you in error and the e-mail
contains patient information, please contact the Partners Compliance HelpLine at
http://www.partners.org/complianceline . If the e-mail was sent to you in error
but does not contain patient information, please contact the sender and properly
dispose of the e-mail.

signature.asc (507 bytes) Download Attachment
Reply | Threaded
Open this post in threaded view
|

Re: Image Filters

Andras Lasso-2
Image Filters

 

“Is there any image filter or method that can be used to change a detailed US or MR image into a solid coloured binary image?”

=> This operation is called segmentation. There are several segmentation methods in Slicer that you may use.

 

Note that intensity-based registration algorithms are not optimal for binary images. Recommended solutions:

A.      Convert the binary images to grayscale distance map images and register those

B.      Create models from your binary images and register them using ICP

C.      Segment only one image, create a model from that, and then use TubeTK’s model-to-image registration feature.

 

I don’t think there are readily usable Slicer modules for these, so you have to use SimpleITK and VTK (they are available in Slicer through Python scripting and the SimpleFilters).

 

Andras

 

 

From: [hidden email] [mailto:[hidden email]] On Behalf Of Dominik Meier
Sent: June 19, 2014 9:24 AM
To: Strugari, Matthew SCA
Cc: [hidden email]
Subject: Re: [slicer-users] Image Filters

 

Hi Matthew

 

Sounds like an interesting application. Did you find registration to work better with a binary image than the original one?  I'm wondering if there is not something that can be done at the point of registration that would avoid this step. In general the grayscale information helps make registrations more robust, although there are cases with distracting content that can make things worse. Could you give us a brief description of the data you're registering? Maybe there's alternatives.

 

Best,

Dominik

 

 

 

 

On Jun 18, 2014, at 5:34 PM, Alireza Mehrtash <[hidden email]> wrote:



Hi Matthew,

 

You can use BinaryThresholdImageFilter from "Simple Filters" module. 

 

Alireza

 

 

On Jun 18, 2014, at 4:38 PM, Strugari, Matthew SCA <[hidden email]> wrote:



Hi,

Is there any image filter or method that can be used to change a detailed US or MR image into a solid coloured binary image? I would like to remove the detail from my volumes so that I am registering with a single coloured/grayscale volume.

Thanks.
Matthew

_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject
http://www.slicer.org/slicerWiki/index.php/Documentation/4.3/FAQ

 


_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject
http://www.slicer.org/slicerWiki/index.php/Documentation/4.3/FAQ


The information in this e-mail is intended only for the person to whom it is
addressed. If you believe this e-mail was sent to you in error and the e-mail
contains patient information, please contact the Partners Compliance HelpLine at
http://www.partners.org/complianceline . If the e-mail was sent to you in error
but does not contain patient information, please contact the sender and properly
dispose of the e-mail.
Reply | Threaded
Open this post in threaded view
|

Re: Image Filters

Strugari, Matthew SCA
RE: [slicer-users] Image Filters

Hi Andras,

I am not looking to segment my images since I already have prostate and DIL segmentations for the MR and US data. I am just looking for a method to optimize the DSC and Hausdorff distances for the prostate segmenations as well as the DIL segmentations. Seeing as the majority of registration algorithms implemented in Slicer are intensity based, I will look into one of the methods you recommended.

Thanks.
Matthew



-----Original Message-----
From: Andras Lasso [[hidden email]]
Sent: Thu 6/19/2014 11:00
To: Dominik Meier; Strugari, Matthew SCA
Cc: [hidden email]
Subject: RE: [slicer-users] Image Filters


"Is there any image filter or method that can be used to change a detailed US or MR image into a solid coloured binary image?"
=> This operation is called segmentation. There are several segmentation methods in Slicer that you may use.

Note that intensity-based registration algorithms are not optimal for binary images. Recommended solutions:

A.      Convert the binary images to grayscale distance map images and register those

B.      Create models from your binary images and register them using ICP

C.      Segment only one image, create a model from that, and then use TubeTK's model-to-image registration feature.

I don't think there are readily usable Slicer modules for these, so you have to use SimpleITK and VTK (they are available in Slicer through Python scripting and the SimpleFilters).

Andras


From: [hidden email] [[hidden email]] On Behalf Of Dominik Meier
Sent: June 19, 2014 9:24 AM
To: Strugari, Matthew SCA
Cc: [hidden email]
Subject: Re: [slicer-users] Image Filters

Hi Matthew

Sounds like an interesting application. Did you find registration to work better with a binary image than the original one?  I'm wondering if there is not something that can be done at the point of registration that would avoid this step. In general the grayscale information helps make registrations more robust, although there are cases with distracting content that can make things worse. Could you give us a brief description of the data you're registering? Maybe there's alternatives.

Best,
Dominik




On Jun 18, 2014, at 5:34 PM, Alireza Mehrtash <[hidden email]<[hidden email]>> wrote:


Hi Matthew,

You can use BinaryThresholdImageFilter from "Simple Filters" module.

Alireza


On Jun 18, 2014, at 4:38 PM, Strugari, Matthew SCA <[hidden email]<[hidden email]>> wrote:



Hi,

Is there any image filter or method that can be used to change a detailed US or MR image into a solid coloured binary image? I would like to remove the detail from my volumes so that I am registering with a single coloured/grayscale volume.

Thanks.
Matthew
_______________________________________________
slicer-users mailing list
[hidden email]<[hidden email]>
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email]<[hidden email]> with unsubscribe as the subject
http://www.slicer.org/slicerWiki/index.php/Documentation/4.3/FAQ



_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject
http://www.slicer.org/slicerWiki/index.php/Documentation/4.3/FAQ


The information in this e-mail is intended only for the person to whom it is
addressed. If you believe this e-mail was sent to you in error and the e-mail
contains patient information, please contact the Partners Compliance HelpLine at
http://www.partners.org/complianceline . If the e-mail was sent to you in error
but does not contain patient information, please contact the sender and properly
dispose of the e-mail.